© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78066
    Prev
    Next
    INDEX
    Explanations

    Names and places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Baillargeon
    -0.74
     myſelf
    -0.71
    awtextra
    -0.70
    énario
    -0.68
     raiſ
    -0.67
    ollectionView
    -0.66
     ſtill
    -0.65
     ſub
    -0.64
     fubject
    -0.64
     aſ
    -0.63
    POSITIVE LOGITS
    ContextHolder
    0.54
     AssemblyProduct
    0.49
    espé
    0.48
    anggung
    0.46
    TemporalType
    0.41
    呂
    0.41
    andExpect
    0.41
     Society
    0.41
     society
    0.40
     SOCIETY
    0.40
    Activations Density 0.000%

    No Known Activations